tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-05 08:28:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

initial jina-embeddings-v3 support

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-05-21 20:17:35 +02:00
committed by GitHub
parent 8e186ef0e7
commit 6303ea2640
2 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/tensor_mapping.py
View File

@@ -157,6 +157,7 @@ class TensorNameMap:
"h.{bid}.attn.c_attn", # gpt2
"transformer.h.{bid}.mixer.Wqkv", # phi2
"encoder.layers.{bid}.attn.Wqkv", # nomic-bert
"encoder.layers.{bid}.mixer.Wqkv", # jina-bert-v3
"model.layers.{bid}.self_attn.qkv_proj", # phi3
"encoder.layers.{bid}.self_attention.query_key_value", # chatglm
"transformer.layers.{bid}.attn.qkv_proj", # openelm
@@ -224,6 +225,7 @@ class TensorNameMap:
"model.layers.layers.{bid}.self_attn.o_proj", # plamo
"model.layers.{bid}.attention.wo", # internlm2
"encoder.layers.{bid}.attn.out_proj", # nomic-bert
"encoder.layers.{bid}.mixer.out_proj", # jina-bert-v3
"transformer.decoder_layer.{bid}.multi_head_attention.linear", # Grok
"transformer.blocks.{bid}.norm_attn_norm.attn.out_proj", # dbrx
"encoder.layers.{bid}.self_attention.dense", # chatglm